Summary of Guiding and Diversifying Llm-based Story Generation Via Answer Set Programming, by Phoebe J. Wang et al.
Guiding and Diversifying LLM-Based Story Generation via Answer Set Programming
by Phoebe J. Wang, Max Kreminski
First submitted to arxiv on: 1 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel approach to generating diverse stories by combining the strengths of instruction-tuned large language models (LLMs) with symbolic story generation techniques. Specifically, it uses answer set programming (ASP) to provide high-level guidance for LLM-based story generation. The approach is demonstrated to produce more diverse stories than an unguided LLM via semantic similarity analysis. Additionally, the paper highlights the improved compactness and flexibility of ASP-based outline generation over full-fledged narrative planning. This work has implications for natural language processing (NLP) and creative AI applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research combines two different ways to generate stories: one uses big language models, and the other uses symbolic logic. The goal is to make story generation more diverse and flexible. They show that by using a high-level plan created with symbolic logic, they can get more varied stories than just relying on the language model alone. This work could lead to new ways of creating stories, poems, or even dialogues in AI systems. |
Keywords
* Artificial intelligence * Language model * Natural language processing * Nlp
